CRAFT™️ Experiment: Copilot: Rethinking A.I. Data Types (5 of 5)
THE CRAFT™️ EXPERIMENT :: WEEK 3 :: POST 5
< Previous Page | Page 4 of 5 | Next Page >
Copilot: Rethinking A.I. Data Types
-
PROMPT:
Please read the attached project files.
# 01 - INITIAL PROMPT
PROMPT: "Hi, we will work together to brainstorm some content for my website. To begin, I will provide a 10-part prompt that will describe the following:
1. Personal Introduction: Who I am.
2. Content/Website Purpose: The website for which the content will be created and its intended purpose. This provides context for the chat.
3. About the Audience and Website : Target Audience, Pain Points & Unique Value Proposition, Competitive Edge and Elevator Pitch.
4. Content Goals: The objectives to achieve with the content.
5. Role of the A.I.: The expected role that you , the A.I. chat service, should assume in this process.
6. Content Source: The source from which the content will be derived.
7. Inspirations: Inspirations to guide you , the A.I. chat service, in understanding the type of content to create.
8. Constraints: Any specific constraints or aspects to avoid in the content creation process.
9. Ideas for visuals: Any ideas that I have for visuals that may be included in this content. Please do not create these visuals unless specifically asked to do so.
10. Related Stories/Content: If this content is part of a series, this will list and briefly explain the series and list any helpful URLS.
1) Personal Background and Site Overview - Based in Minneapolis, MN, USA, I am a professional in Computer Science and Graphic Design. I work for a Fortune 100 Company as a Senior Cybersecurity Incident Responder where I work with a team to keep people safe from cybersecurity attacks. In addition to 6 years in cybersecurity, my professional history includes 10 years as an Identity Designer and 10 years as an entrepreneur.
2) Website Content Purpose : the website is located at www.ketelsen.ai and is part of the blog section. Ketelsen.ai is An Ongoing AI prompt crafting Experiment. Ketelsen.ai is where the raw brainstorming and AI prompt engineering happens. Think of it as a lab where you consistently test out new prompt ideas, integrate various AI tools (ChatGPT, Midjourney, etc.), and see what sticks. The website features an Exclusive Prompt Collection with over 1,000 in-depth AI prompts covering real-world problems. These prompts are generated each week by multiple AI services, each with its own strengths. The website's Focus is on Breadth & Innovation. The site showcases new and creative ways to use AI—often pushing boundaries by running repeated “what if” experiments with different AI models. Because the goal is to innovate, Ketelsen.ai’s prompts can be very detailed (and at times, a bit overwhelming for newcomers).
3) About the Website:
Important details about Ketelsen.ai:
Step 1: Target Audience
• Demographics: Ages 25–45, global (English-speaking), professionals or entrepreneurs with moderate to high discretionary income.
• Psychographics:
○ Enthusiastic about AI-driven innovation and efficiency.
○ Enjoy experimenting with new technology but can feel overwhelmed by the sheer volume of AI options.
○ Prefer transparent “behind-the-scenes” exploration of prompt engineering.
• Persona Snapshot:
○ “Alex the AI Trailblazer”: 33-year-old product manager at a startup, craves cutting-edge AI prompts and advanced experimentation, wants to stay ahead with minimal wasted time.
Step 2: Pain Points & Unique Value Proposition
Top 3 Pain Points
1. Overwhelm by AI Options: Too many prompts/models to choose from, causing decision fatigue.
2. Difficulty Crafting Effective Prompts: Need guidance to avoid mistakes and harness AI fully.
3. Time Constraints for Testing: Users want quick, reliable feedback on what works without lengthy trial and error.
UVP (1–2 Sentences)
“Ketelsen.ai delivers a constantly evolving library of advanced AI prompts—over 1,000 and counting—so tech-savvy entrepreneurs can rapidly experiment without wasting time on guesswork. By focusing on real-world testing and transparent experimentation, it offers a more expansive and in-depth resource than other popular prompt-engineering websites.”
Step 3: Competitive Edge
1. Massive Prompt Library (over 1,000 and growing).
2. Real-Time Experimentation: Transparent and ongoing updates.
3. Behind-the-Scenes Insight: Detailed explanations of how and why prompts work.
4. Efficiency-Focused: Built around minimal time investment, demonstrating how to achieve more with less.
5. Constant Innovation: Early adoption of new AI models and features.
Step 4: Elevator Pitch
“At Ketelsen.ai, we empower tech-savvy entrepreneurs and AI enthusiasts to unlock cutting-edge automation with minimal time investment. By offering a massive, ever-growing library of high-impact prompts—backed by real-world experimentation and robust behind-the-scenes insights—we help you stay ahead in AI innovation without sacrificing your schedule. It’s your sandbox for AI exploration.”
4) Content Goals - The AI chat responses should result in real prompts that a real entrepreneur can use to achieve a real task. The task will be explained following this.
5) Role of the A.I. - You are “an expert in creating prompts for ChatGPT, Google GEMINI, Anthropic Claude and other similar Gen AI Tools” . You are creative and can use these Gen AI Tools in creative ways.
6) Content Source - Use any resource that is needed to achieve the objectives.
7) Inspirations for Content - The content style should be fun, entertaining and informative. Since the target audience for this site is entrepreneurs , the style should be similar to content found in popular media created for this market such as Forbes, Fortune, and the Wall Street Journal.
8) Constraints -
- Please do not make up any fake information, if there is no data or actual factual information, please respond with "NOT APPLICABLE"
9) Ideas for visuals - More information to come on this
10) Related Stories/Content - This article is part of the ketelsen.ai series on CRAFT™️ is an acronym for Configurable Reusable AI Framework Technology. CRAFT™️ is an on-going weekly experiment where I will be working together with the world’s most advanced commercially available A.I.s to develop a new way way to communicate with A.I. while adapting the principals of Object Orientated Programming to AI Chats. The goal is deeper, more intuitive and more meaningful interactions with A.I. chat tools.
Before continuing the next set of instructions, please list any items that need clarification. If there are no questions, please respond with ""READY"".
RESPONSE: READY
PROMPT:
Based on analysis of modern AI engineering needs, I am considering new specialized data types. These data types will make CRAFT code more expressive and easier to understand while reducing boilerplate. They are concepts that any A.I. can understand without defining them (for example: users do not need to explain to a A.I. Chat what a prompt is because the A.I. knows this term and what a prompt is and what it cannot be). Here are some ideas that I have:
Communication & Context Data Types
Intent: Represents a user's goal or purpose in an interaction
Example: Intent("book_flight", confidence=0.92)
Value: Helps AI understand what users want to accomplish without explicit instructions
Entity: Named pieces of information extracted from text
Example: Entity("destination", "Paris", category="location")
Value: Identifies key information points without complex parsing code
Sentiment: Emotional tone in text or speech
Example: Sentiment("positive", confidence=0.87)
Value: Enables emotional intelligence in AI responses
DialogueContext: Maintains conversation state with history and reference points
Example: DialogueContext(turns=5, current_topic="booking_details")
Value: Simplifies building conversational flows
Content & Media Data Types
RichContent: Text with formatting, links, and media
Example: RichContent("Check this important [resource](https://example.com)")
Value: Represents formatted content without HTML/Markdown boilerplate
MediaReference: Standardized reference to image, audio, or video
Example: MediaReference("image", url="https://example.com/img.jpg", alt="Product photo")
Value: Consistent handling of media across different AI platforms
Summary: Condensed version of longer content
Example: Summary("Long meeting transcript...", max_length=100)
Value: Standardizes content summarization without repetitive prompting
Business & Analytics Data Types
UserProfile: Collection of user preferences and behaviors
Example: UserProfile(industry="healthcare", role="manager", interests=["AI", "automation"])
Value: Provides context for personalized AI interactions
Metric: Named value with unit and context
Example: Metric("conversion_rate", 3.2, unit="percent", trend="increasing")
Value: Standardized business KPI representation
TimeSeries: Temporal sequence of data points
Example: TimeSeries([{date: "2025-04-01", value: 120}, ...], metric="sales")
Value: Simplifies trend analysis and forecasting
Annotation: Comments or notes attached to content
Example: Annotation("This paragraph needs revision", severity="suggestion")
Value: Standardizes feedback and collaboration
Functional Data Types
ActionTemplate: Reusable pattern for AI actions
Example: ActionTemplate("email_customer", parameters=["name", "order_id"])
Value: Creates standardized workflows for common business processes
DataValidator: Rules for validating input
Example: DataValidator(type="email", required=true, format="corporate")
Value: Ensures data quality without complex validation code
Transformation: Data conversion specification
Example: Transformation("csv_to_table", options={"headers": true})
Value: Standardizes data processing steps
Why These Align With CRAFT Objectives
These data types align with your objectives because they:
Reduce boilerplate: Replace complex code patterns with simple, declarative structures
Increase expressiveness: Clearly communicate intent without lengthy documentation
Are universally understood by AI: Represent concepts that all modern AI systems understand innately
Are accessible to non-technical users: Use business-friendly terminology rather than technical jargon
Enable practical applications: Focus on common business scenarios that entrepreneurs encounter daily
Each type provides a clear, practical benefit that would be immediately recognizable to your target users, making the CRAFT framework more intuitive and productive for AI-assisted tasks in business contexts.
Beginner-Friendly Data Types for CRAFT Framework
For AI beginners with less than a year of experience, we need data types that are immediately intuitive, self-explanatory, and relate to familiar concepts. Here are data types that would make CRAFT more accessible to newcomers:
Learning & Guidance Data Types
Template: Ready-to-use prompt structures with placeholders
Example: Template("product_description", slots=["product_name", "features", "target_audience"])
Value: Helps beginners follow proven patterns without reinventing prompts
Example: Sample inputs and outputs for reference
Example: Example(input="Summarize climate change", output="Climate change refers to...")
Value: Shows concrete results to help beginners understand what's possible
Feedback: Guidance on improving prompts
Example: Feedback("Add more specific details about your target audience")
Value: Provides built-in coaching to accelerate learning
Simplified Task Data Types
Question: Simple query for information
Example: Question("What are the benefits of solar energy?")
Value: Clarifies that the AI should focus on providing information
Instruction: Clear direction for the AI to follow
Example: Instruction("Write a professional email to a client about a project delay")
Value: Makes it explicit when users want the AI to create something
Comparison: Request to evaluate alternatives
Example: Comparison("electric vs. gas vehicles", aspects=["cost", "environment", "convenience"])
Value: Structures a common task in a format AI can consistently understand
Everyday Content Data Types
Email: Email structure with essential components
Example: Email(subject="Meeting Follow-up", recipient="team", tone="professional")
Value: Simplifies a common business task with natural parameters
SocialPost: Content formatted for social media
Example: SocialPost(platform="LinkedIn", topic="industry trend", hashtags=3)
Value: Handles platform-specific considerations automatically
Note: Quick, informal content for personal use
Example: Note("Remember to check quarterly numbers before the meeting")
Value: Distinguishes casual content from formal documents
Learning Support Data Types
Explanation: Request for concept clarification
Example: Explanation("machine learning", level="beginner", examples=true)
Value: Gets consistent educational content with appropriate depth
HowTo: Step-by-step instructions for a process
Example: HowTo("create a budget spreadsheet", detail_level="medium")
Value: Ensures AI provides actionable, sequential steps
Definition: Simple meaning of a term
Example: Definition("prompt engineering", context="AI")
Value: Quick access to clear explanations without overwhelming detail
Communication Helper Data Types
Tone: Writing style specification
Example: Tone("friendly", "professional", "concise")
Value: Simplifies one of the most common adjustments beginners make
Audience: Target reader description
Example: Audience("marketing professionals", knowledge_level="intermediate")
Value: Helps AI tailor content appropriately without complex instructions
Length: Content size specification
Example: Length("paragraph", count=3) or Length("words", count=200)
Value: Ensures consistent output format without technical parameters
Why These Are Beginner-Friendly
These data types are designed specifically for AI beginners because they:
Use everyday language: No technical jargon or complex concepts
Match how beginners think: Align with natural questions and requests
Provide structure: Guide users toward successful interactions
Focus on common tasks: Address the needs beginners have most frequently
Reduce complexity: Hide advanced parameters behind simple interfaces
Build transferable skills: Teach concepts that apply across all AI systems
For a beginner, being able to say Instruction("Write a blog post").with(Topic("sustainable fashion")).using(Tone("casual", "informative")) is much more intuitive than crafting complex prompts from scratch.
These types create a structured yet flexible way for newcomers to create effective AI interactions while gradually learning deeper prompt engineering concepts.
Do you agree with these suggestions? Please evaluate these data types given the objectives of the CRAFT frameowrk.
Are any of these data types likely to be confusing for either the user or the A.I.?
These ideas are very much in line with the CRAFT framework’s goal of making AI interactions both expressive and efficient. The concepts you’ve introduced provide a structured vocabulary that encapsulates common intents and tasks, reducing boilerplate while immediately conveying meaning to both the AI and human users. Let’s break down the evaluation by category:
Communication & Context Data Types
Intent, Entity, Sentiment, DialogueContext: These types tap into well-established NLP concepts.
Intent captures the overall goal (e.g., booking a flight) without bundled explanations.
Entity isolates critical details (like locations), ensuring that the AI extracts the right tokens.
Sentiment gives your responses an emotional shape, which is increasingly expected by users.
DialogueContext manages the conversation history, enabling more fluid conversational flows.
These types not only reduce the need for verbose explanations but also align directly with modern AI systems’ internal representations. They’re clear, intuitive to most users familiar with conversational AI concepts, and help maintain context throughout multi-turn interactions.
Content & Media Data Types
RichContent and MediaReference:
RichContent abstracts formatted text, links, and media, meaning users don’t have to worry about embedding raw HTML or Markdown manually.
MediaReference standardizes handling assets like images or videos regardless of the platform.
Summary: Offers a mechanism to condense long texts into digestible snippets without rephrasing the prompt every time.
They encapsulate common tasks in content management while reducing boilerplate code. They are mostly self-explanatory—with proper documentation, users should easily understand how to integrate and leverage these types across different AI platforms. One minor note is ensuring that additional parameters (such as alt text for media) are clearly defined when contexts diverge (e.g., audio vs. video), but overall the approach is solid.
Business & Analytics Data Types
UserProfile, Metric, TimeSeries, Annotation: These types provide a standardized approach for expressing business insights and analytics:
UserProfile aggregates user data for targeted interactions.
Metric and TimeSeries allow you to handle KPIs and trends in a uniform way.
Annotation facilitates collaborative feedback with standardized notes.
They address core business use cases by turning ad hoc data representations into structured, reusable objects. This aligns with CRAFT’s objective of making the framework applicable to real-world business scenarios. It’s important, however, that users are given clear examples so they understand the expected format (such as date formats or units for metrics) to avoid misinterpretations.
Functional Data Types
ActionTemplate, DataValidator, Transformation: These abstractions streamline recurring processes:
ActionTemplate standardizes workflows (e.g., emailing customers) without forcing users to recreate similar prompts repeatedly.
DataValidator ensures correctness in inputs, which is key for reliable outcomes.
Transformation abstracts data conversion steps, providing clarity and consistency.
They are a powerful way to embed business process logic directly into the prompt framework. The key is to maintain clear boundaries and definitions so that each type’s responsibility doesn’t overlap with another’s—a potential pitfall if definitions aren’t rigorously documented.
Beginner-Friendly Data Types
Template, Example, Feedback, Question, Instruction, Comparison, Email, SocialPost, Note, Explanation, HowTo, Definition, Tone, Audience, Length: This suite is designed to minimize the learning curve:
Template and Example provide immediate models and reference outputs.
Feedback offers built-in coaching for refining prompts.
Instruction, Question, and Comparison clearly distinguish between creating content, querying information, and evaluating alternatives.
Everyday content types like Email, SocialPost, Note help users execute common tasks with natural language parameters.
Learning support types like Explanation, HowTo, Definition make advanced concepts accessible.
Communication helpers like Tone, Audience, Length allow immediate adjustments in style without complex parameter-tweaking.
These are exceptionally friendly for beginners because they use familiar language and clear roles. The potential challenge here is ensuring that the distinctions between similar-sounding types (e.g., Feedback vs. Annotation vs. Explanation) are well documented. With explicit guidelines and examples, though, this risk is minimal while their benefits in clarity and ease-of-use are significant.
Overall Assessment & Alignment With CRAFT Objectives
Reduction of Boilerplate & Increased Expressiveness: Each proposed type serves to encapsulate frequently repeated patterns into a clear, one-line declaration. This dramatically reduces the amount of scaffolding a user needs to set up their prompt interactions, aligning with CRAFT’s emphasis on token conservation and clarity.
Universally Recognized Concepts: By using terms like Intent, Entity, or DialogueContext, these data types lean on concepts that are already well understood in modern AI and NLP research. This familiarity aids both the AI (in parsing intentions) and the user (in constructing prompts).
Accessibility for Non-Technical Users: The beginner-friendly types make it easier for those with limited technical experience to engage in advanced AI interactions without needing in-depth knowledge of coding. They bridge the gap between natural language and technical specification in a very tangible way.
Potential Areas of Confusion:
The line between similar types (for example, Feedback vs. Annotation vs. Explanation) could blur if not clearly documented.
Some types like Tone and Length require a precise definition of acceptable values (e.g., is Tone a single string or multiple adjectives?) to avoid ambiguity.
Overlapping functionality between Instruction and Question might need contextual differentiation—ensuring that when to use one over the other is made explicit in documentation.
With meticulous documentation, versioned examples, and perhaps even a few interactive demos embedded in the framework’s onboarding materials, these risks can be effectively managed.
Final Thoughts
I fully agree with your suggestions. They resonate with modern AI engineering practices by abstracting common patterns into well-defined, self-explanatory data types. This not only enhances the expressive power of the CRAFT framework but also broadens its accessibility to both technical and non-technical users. Provided that clear documentation is provided and potential overlaps in terminology are addressed through thoughtful naming conventions and examples, these updates have the potential to significantly improve the usability and efficiency of AI interactions.
Please suggest new data types that fit this objective.
Below are some new, specialized data types that can help make CRAFT even more expressive and streamlined. I’ve broken them into several categories to align with modern AI engineering goals, while ensuring they’re approachable—even for beginners.
Communication & Context Data Types
InteractionHistory Description: Automatically captures key details from each conversational turn. It stores a list of turns including detected intents, sentiment, topics, and any follow-up actions. Example:
python
InteractionHistory(turns=[ {"intent": "book_flight", "sentiment": "positive", "topic": "travel"}, {"intent": "confirm_booking", "sentiment": "neutral", "topic": "confirmation"} ])
Value: Reduces boilerplate by automatically gathering context, so subsequent interactions need less manual state management.
MetaData Description: Encapsulates transaction-level details such as timestamps, device types, version identifiers, or source labels. Example:
python
MetaData(timestamp="2025-05-04T12:34:56Z", source="web", version="v25a")
Value: Provides essential context without extra explanation, making it easy for the AI to adjust outputs based on environmental factors.
Content & Media Data Types
InteractiveContent Description: Represents content designed for user interaction—enabling dynamic behaviors like expanding sections or in-place updates. Example:
python
InteractiveContent(text="View more details", actions=["expand", "collapse"])
Value: Lets creators encapsulate behavior along with content, minimizing additional coding for interactive elements.
VisualLayout Description: Standardizes layout instructions for content display. It covers information on alignment, spacing, columns, and grid systems without needing raw CSS or HTML. Example:
python
VisualLayout(columns=3, gutter=20, alignment="center")
Value: Abstracts visual design details so that the focus remains on content creation rather than presentation code.
VoiceTone Description: Specifies parameters for audio or voice-based responses, including style, pace, and pitch. Example:
python
VoiceTone(style="energetic", pace="moderate", pitch="medium")
Value: Enhances multimedia content by directly controlling the tone of generated voice outputs, making it easier for the system to adjust to desired brand voices.
Business & Analytics Data Types
ConversionEvent Description: Captures discrete business events that lead to user conversion. This type centralizes attributes like event name, counts, rates, and time stamps. Example:
python
ConversionEvent(name="signup", count=20, conversion_rate=12.5)
Value: Standardizes the tracking of conversion-related events, facilitating efficient reporting without custom event management code.
CustomerFeedback Description: Provides a structured format for collecting customer insights by combining ratings, comments, and optional suggestions. Example:
python
CustomerFeedback(rating=4, comment="The interface feels intuitive and engaging.")
Value: Streamlines data gathering on user experiences, directly feeding into iterative improvement processes.
MarketSignal Description: Represents external signals or trends with a confidence metric, such as rising demand in a particular market segment. Example:
python
MarketSignal(signal="increasing_demand", confidence=0.80)
Value: Integrates strategic market intelligence into the system without extra manual data analysis.
Functional Data Types
WorkflowStep Description: Encapsulates a single step in a multi-stage process by defining conditions and the corresponding actions. Example:
python
WorkflowStep("validate_input", conditions=["non_empty"], actions=["send_to_processing", "log_error"])
Value: Makes it simple to outline complex logic using discrete, reusable modules—streamlining workflow construction.
QueryChain Description: Links several processing steps or queries into one chain. Each step’s output flows into the next, representing complex tasks as a sequence. Example:
python
QueryChain(steps=["fetch_data", "analyze_data", "generate_report"])
Value: Reduces the need for verbose instructions by chaining logically connected actions into a single definition.
Condition Description: Standardizes conditional logic operators used across various workflows, wrapping field comparisons into an object. Example:
python
Condition(field="user_role", operator="equals", value="administrator")
Value: Clarifies and encapsulates decision-making criteria, minimizing ambiguity without littering code with inline if-statements.
Learning Support & Beginner-Friendly Data Types
GuidanceTip Description: Offers brief, in-line hints or best practices directly within the framework, tailored to the user’s current task. Example:
python
GuidanceTip("Consider specifying your target audience for more tailored outputs.")
Value: Helps beginners navigate prompt creation by providing context-sensitive tips, reducing the learning curve.
PeerExample Description: Provides illustrative examples by pairing input and output samples that have worked effectively in similar scenarios. Example:
python
PeerExample(input="Create a product review", output="This product revolutionized my workflow...")
Value: Acts as an immediate reference, empowering users with concrete examples to model their own prompts on.
InteractiveTutorial Description: Embeds an onboarding module within the framework that guides users through prompt crafting with step-by-step activities. Example:
python
InteractiveTutorial("PromptCraft101", steps=["Introduction", "Hands-On Practice", "Review"])
Value: Provides a built-in learning path, making advanced prompt engineering more accessible from day one.
Communication Helper Data Types
Persona Description: Defines a target user persona with attributes like name, goals, characteristics, and preferred tone. Example:
python
Persona(name="Tech Savvy Marketer", goals=["increase engagement"], tone="professional")
Value: Instantly aligns the content to the intended audience, ensuring the generated prompts are both targeted and contextually apt.
StyleGuide Description: Centralizes branding or stylistic rules—such as color palettes, typography, layout guidelines—into a single, reusable reference. Example:
python
StyleGuide(color_palette=["#003366", "#FFFFFF"], font_family="Helvetica", layout="responsive")
Value: Ensures consistent communication and branding across outputs, further reducing the need for per-prompt style adjustments.
EngagementMetric Description: Consolidates common engagement metrics (like scroll depth or session time) into a standardized data format. Example:
python
EngagementMetric(metric="scroll_depth", value=75, unit="percent")
Value: Helps track and compare user engagement objectively across different content pieces.
Additional Utility Data Types
ExperimentConfig Description: Holds configuration settings for A/B testing or multivariate experiments, including target groups and parameters. Example:
python
ExperimentConfig(test_group="A", parameters={"layout": "grid", "color_scheme": "dark"})
Value: Simplifies the setup and management of experiments, fostering a data-driven approach to prompt optimization.
PromptVariant Description: Encapsulates multiple versions of a prompt meant for testing different outcomes, tagged with performance indicators. Example:
python
PromptVariant(id="variant_1", content="Prompt version A with structured format", target="conversion")
Value: Facilitates streamlined multivariate testing within the CRAFT environment, leading to better-informed improvements.
DataSource Description: Specifies metadata about the source of data used in prompt generation, including its reliability, frequency of updates, and origin. Example:
python
DataSource(source="internal_API", reliability="high", update_frequency="daily")
Value: Enhances transparency and trust in the data powering generated content, ensuring consistent quality.
How These Data Types Enhance CRAFT
Expressiveness & Clarity: Each data type encapsulates a discrete idea, offering a clear, concise way to set up complex instructions and workflows. This minimizes the need for repetitive code and lengthy prompt explanations.
Reduced Boilerplate: By defining common patterns (from tracking conversation context to specifying experimental parameters) as dedicated data types, users have fewer details to rewrite and reformat for every new project.
Ease of Use for Beginners: With intuitive names and clear examples, even those new to AI prompt engineering can quickly understand and leverage these types. They act as both functional tools and educational aids.
Universally Recognized Concepts: Drawing from modern NLP and software engineering practices, these types use familiar terminology (like Condition, WorkflowStep, or Persona), which is inherently understood by AI systems and experienced users alike.
